From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-pf0-f172.google.com ([209.85.192.172]:45797 "EHLO mail-pf0-f172.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751745AbeBTXVj (ORCPT ); Tue, 20 Feb 2018 18:21:39 -0500 Received: by mail-pf0-f172.google.com with SMTP id j24so3140166pff.12 for ; Tue, 20 Feb 2018 15:21:39 -0800 (PST) Message-ID: <1519168897.55655.31.camel@gmail.com> Subject: Re: [PATCH net-next 0/6] tcp: remove non GSO code From: Eric Dumazet To: Oleksandr Natalenko Cc: Eric Dumazet , "David S . Miller" , netdev , Neal Cardwell , Yuchung Cheng , Soheil Hassas Yeganeh Date: Tue, 20 Feb 2018 15:21:37 -0800 In-Reply-To: <2638137.lzCXOlOYsz@natalenko.name> References: <20180219195652.242663-1-edumazet@google.com> <1519157377.55655.26.camel@gmail.com> <2638137.lzCXOlOYsz@natalenko.name> Content-Type: text/plain; charset="UTF-8" Mime-Version: 1.0 Content-Transfer-Encoding: 8bit Sender: netdev-owner@vger.kernel.org List-ID: On Tue, 2018-02-20 at 21:45 +0100, Oleksandr Natalenko wrote: > On úterý 20. února 2018 21:09:37 CET Eric Dumazet wrote: > > Also you can tune your NIC to accept few MSS per GSO/TSO packet > > > > ip link set dev eth0 gso_max_segs 2 > > > > So even if TSO/GSO is there, BBR should not use sk->sk_gso_max_segs to > > size its bursts, since burt sizes are also impacting GRO on the > > receiver. > > net-next + 7 patches (6 from the patchset + this one). My latest patch (fixing BBR underestimation of cwnd) was meant for net tree, on a NIC where SG/TSO/GSO) are disabled. ( ie when sk->sk_gso_max_segs is not set to 'infinite' ) It is packet scheduler independent really. Tested here with pfifo_fast, TSO/GSO off. Before patch : for f in {1..5}; do ./super_netperf 1 -H lpaa24 -- -K bbr; done     691 (ss -temoi shows cwnd is stuck around 6 )     667     651     631     517 After patch : # for f in {1..5}; do ./super_netperf 1 -H lpaa24 -- -K bbr; done    1733 (ss -temoi shows cwnd is around 386 )    1778    1746    1781    1718 Thanks.